Interactive Reinforcement Learning for Object Grounding via Self-Talking.

Yan Zhu Shaoting Zhang Dimitris N. Metaxas

Published in: CoRR (2017)

Keyphrases

reinforcement learning
function approximation
state space
d objects
user interaction
multi agent
moving objects
model free
keypoints
complex objects
reinforcement learning algorithms
object model
optimal control
spatial relations
data objects
virtual reality
optimal policy
mobile robot
learning process
viewpoint